llama.cpp
Local LLM RunnersHigh-performance LLM inference in plain C/C++
Replaces OpenAI API
Best No-Database Local LLM Runners for self-hosting
The 6 best No-Database local llm runners you can self-host, ranked by community traction.
MLC LLM
Local LLM RunnersUniversal LLM deployment engine for any hardware
Replaces OpenAI API
KoboldCpp
Local LLM RunnersSingle-file local LLM runner for text and storytelling
Replaces ChatGPT
Petals
Local LLM RunnersRun large language models collaboratively in a swarm
Replaces OpenAI API
Aphrodite Engine
Local LLM RunnersHigh-throughput inference engine for large language models
Replaces OpenAI API
Wllama
Local LLM RunnersRun LLM inference directly in the browser with WebAssembly
Replaces OpenAI API
No apps match these filters.
At a glance
| App | Deploy effort | Difficulty | Min. RAM | License | ★ Stars |
|---|---|---|---|---|---|
| llama.cpp | Under-an-hour setup | Hard | 8,192 MB | MIT | 131,102 |
| MLC LLM | Read-the-docs project | Hard | 4,096 MB | Apache-2.0 | 23,239 |
| KoboldCpp | Read-the-docs project | Easy | 8,192 MB | AGPL-3.0 | 11,993 |
| Petals | Under-an-hour setup | Hard | 8,192 MB | MIT | 10,629 |
| Aphrodite Engine | Under-an-hour setup | Hard | 8,192 MB | AGPL-3.0 | 1,874 |
| Wllama | Read-the-docs project | Medium | 512 MB | MIT | 1,333 |
Quick picks
- Most adopted: llama.cpp (131,102 GitHub stars).
- Lightest footprint: Wllama (from 512 MB RAM, against 8,192 MB for the heaviest here).
- Licensing: 3 of 6 use MIT; check the rest individually if you plan to modify and redistribute.
Every option here is open-source and self-hostable, tagged No-Database within the local llm runners category. Deploy effort is graded from published container recipes, not vendor claims — see the methodology.